Tips for Effective Prompt Formulation

How to Write a Prompt to Engage with Generative AI

While using GenAI can be as simple as typing in a question or other prompt, the reality is that it is still not straightforward for the user to get exactly the output that they want. For example, the breakthrough AI image Théâtre D'opéra Spatial which won a prize at the Colorado State Fair in the USA, took weeks of writing prompts and fine-tuning hundreds of images in order to generate the final submission.

How faculty and students engage with GenAI matters. Understanding the concepts of prompts and prompt engineering is crucial for effectively harnessing the power of generative AI in teaching and learning. In case the sound of "prompt engineering" makes you feel nervous or overwhelmed, we thought we'd share this quote from Ethan Mollick's blog post, A guide to prompting AI (for what it is worth):

"The best way to use AI systems is not to craft the perfect prompt, but rather to use it interactively. Try asking for something. Then ask the AI to modify or adjust its output. Work with the AI, rather than trying to issue a single command that does everything you want. The more you experiment, the better off you are". 

The best approach is an interactive one, where the user critically analyzes the GenAI output to further modify or add to the prompt in order to obtain the desired output. With that being said, there is some information and some strategies that will make things easier and more efficient as you interact with GenAI tools. And this is something we all (teachers and learners) need to practice!

Tips for Effective Prompt Writing

A prompt is a specific input given to a generative AI model to initiate its response. It typically consists of a contextualized question or request.

• Be Specific: If you ask a vague question, you may get a vague answer. The more details you provide, the better the response the model will be able to provide. Be specific about what you want, but also be specific about what you don't want! Set limitations/constraints to guide the response.
• State Your Intent: If there's a specific purpose for your question, state it in the prompt.
• Assign a Persona: When appropriate, assign a persona or role to define tone or expertise.
• Include context: include information about level (i.e college -level), audience, discipline to generate relevant and meaningful completions.
• Direct the Output Format: If you want the answer in a specific format, state it in your prompt. Do you want a multiple-choice question? A paragraph? A step-by-step process?
• Refine and iterate as necessary: critically analyze the output and refine your prompt as necessary. Experiment with different variations. If you're not getting the response you want, try asking the question in a different way. The model might understand one phrasing better than another.
• Be ethical: avoid prompts that may generate inappropriate, biased or harmful content.

The following table outlines some prompting techniques, formulas and examples:

Technique	Description	Formula	Example
Clear Intent	Clearly state the desired output or question.	"Generate a output that [condition]".	Generate a summary that captures the main ideas.
Specificity	Be specific about the required content or format.	"Generate a [output] that includes [specific content]".	Generate a poem that rhymes and has 10 lines.
Constraints	Set limitations to guide the response.	"Generate a [output] within [specified constraints]".	Generate a story using only 100 words.
Personas	Assign a persona or role to define tone or expertise.	"Acting as [role], write a [output] about [topic]".	Acting as an expert journalist, write a creative title for this article.
Evaluation	Specify criteria for assessing the response quality.	"Review the [output] against [criteria] and suggest ways to improve.	Review the essay against the rubric and suggest edits.
Style	Specify the desired tone or writing style.	"Generate a [output] in a [specific style]".	Generate a persuasive essay using formal language.

Generative AI tools and Copyright Considerations

The content of this section is evolving and subject to change. Last updated: October 23, 2023

Generative AI tools are evolving quickly and their impact on teaching, learning and research is significant, posing both opportunities and challenges. The following section addresses copyright considerations for faculty, students, and staff at Centennial College.

Are there copyright considerations I need to think about when using Generative AI tools?

Yes. There remains significant legal uncertainty with the use of Generative AI tools and copyright. This is an evolving area and our understanding will develop as new policies, regulations, and case law becomes settled.

Some of the concerns surrounding Generative AI and copyright include:

• Input: The legality of the content used to train AI models is unknown in some cases. There are a number of lawsuits originating from the US that allege Generative AI tools infringe copyright and it remains unclear if and how the fair use doctrine can be applied. In Canada, there also remains uncertainty regarding the extent to which existing exceptions in the copyright framework, such as fair dealing, apply to this activity.

• Output: Authorship and ownership of works created by AI is unclear. Traditionally, Canadian law has indicated that an author must be a natural person (human) who exercises skill and judgement in the creation of a work.²  As there are likely to be varying degrees of human input in content generated, it is unclear in Canada how it will be determined who the appropriate author and owner of works are. More recently, the US Copyright Office has published the following guide addressing these issues: Copyright Registration Guidance for Works Containing AI-Generated Materials

If you would like to use Generative AI tools for content generation, consider the following before doing so:

• Have an understanding that while you can use these tools to create content, you may not own or hold copyright in the works generated 

• Be mindful of what you input into tools: never input confidential information or significant portions of intellectual property you do not have the rights or permissions to. All content entered may become part of the tool's dataset and may inadvertently resurface in response to other prompts

• Review the terms of service of each tool: These terms will dictate use and ownership of input/output and they are subject to change without notice

• Be explicit in how you have used these tools in the creation of your work. Keep a record of prompts and any IP you have used in the creation of output. Review attribution guidelines according to the style guide you are using (refer to the citation library guide or to the following sites: MLA, APA, and Chicago Style). If you are publishing your work, review any requirements or policies that address the use of generative AI tools in your research. These policies will indicate whether AI can be used and how the use of these tools should be disclosed.

Can I use full-text library licensed e-resources (such as journal articles or eBooks) in Generative AI tools like Chat GPT?

No. The library signs contracts with different vendors and publishers, which set out specific terms and conditions that users are responsible for complying with when accessing content. While what is permitted is not uniform across all resources, agreements do not allow for the uploading of copyright protected works to third-party platforms, including generative AI tools.

Can I use the full-text of openly licensed material (such as Creative Commons content) in Artificial Intelligence systems?

Yes. The Creative Commons' FAQs on AI and CC Licenses indicates that "if someone uses a CC-licensed work with any new or developing technology, and if copyright permission is required, then the CC license allows that use without the need to seek permission from the copyright owner so long as the license conditions are respected". Please refer to this Creative Commons resource for further guidance.

What material can I use in a Generative AI tool?

For those interested in exploring Generative AI tools, consider using content that is openly licensed or in the public domain.

---

Source: Centre for Faculty Development and Teaching Innovation, Centennial College, https://ecampusontario.pressbooks.pub/ccgenerativeai/chapter/using-genai-tools-prompts-and-copyright-considerations/
This work is licensed under a Creative Commons Attribution 4.0 License.